--- sourceDocument: Zurich Enable AI sourceDocumentLink: https://www.servicenow.com/docs/r/zurich/intelligent-experiences Release : - zurich ft:locale : - en-US ft:publication_title : - Zurich Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # Reference for Generative AI Controller # Reference for Generative AI Controller {#ariaid-title1} Release version: Zurich Updated July 31, 2025 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 3 minutes to read Summarize ![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) Summarized using AI This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete. ## Summary of Generative AI Controller Reference The Generative AI Controller in the Zurich release (updated July 31, 2025) provides a structured framework within ServiceNow to manage capabilities related to generative AI functions such as summarization, content generation, and prompting. It integrates with Workflow Studio and Virtual Agent Designer to facilitate AI-powered automation and interaction. Show full answer Show less ## Key Tables * **sysoneextendcapability**: Stores generative AI capabilities like Summarize and Generate Content. * **sysoneextendcapabilitydefinition** and **sysoneextenddefinitionattribute**: Define input/output variables for subflows in Workflow Studio; variable names are locked when capabilities are active. * **sysoneextendbuilderconfig** and **sysoneextendbuildercapability**: Link capabilities and providers to builder components in Workflow Studio and Virtual Agent Designer. * **sysoneextendusage**: Tracks each use of capabilities in workflows, agents, and scripts. * **sysgenailogmetadata** and **sysgenerativeailog**: Log detailed AI request and response data, including errors and feedback; HR-related logs are access-restricted. * **sysgenerativeaimetric**: Records performance and safety metrics of LLM responses, such as edit scores and sensitive content triggers. * **sysgenaimodelversionmapping**: Maps AI model versions to providers and configuration metadata for clear model management. ## Key Properties * **com.sn.generative.ai.provider**: Sets the default AI provider when none is specified in a capability definition. * **com.sn.generative.ai.logprompt**: Controls whether AI API calls are logged (default true). * **com.sn.generative.ai.ais.message**: Customizable message shown when AI search finds no answer. * **com.sn.generative.ai.moderation.message**: Message displayed if AI moderation detects inappropriate content. * **com.glide.one.extend.token.buffer**: Defines token buffer size for request validation before executing AI capabilities. * **domain.llm.usage.entitled**: Enables or restricts domain use of Now Assist and LLM processing (default enabled). ## Practical Benefits for ServiceNow Customers * Enables integration of generative AI capabilities within workflows and virtual agents to enhance automation and user interactions. * Provides comprehensive logging and metrics to monitor AI performance, safety, and compliance, facilitating debugging and governance. * Supports secure handling of sensitive data, especially with HR-related logs restricted to authorized administrators. * Allows configuration of AI providers, moderation messaging, and usage entitlements to align with organizational policies and compliance needs. * Facilitates management of AI model versions and mappings for consistent and transparent AI model usage. Reference topics provide information about Generative AI Controller tables, and properties. ## Tables installed {#reference-for-generative-ai-controller__entry__3} | Name | Table | Description | |-|-|-| | OneExtend Capability | sys_one_extend_capability | Generative AI Controller capabilities that include Summarize, Record Summarization, Generate Content, and Generic Prompt. | | OneExtend Capability Definition | sys_one_extend_capability_definition | Attribute configuration for input and output variables for Workflow Studio subflows. | | OneExtend Capability Definition Attribute | sys_one_extend_definition_attribute | Input and output variables for Workflow Studio subflows. Variable names can't be changed if the capability is active and used on the instance. You can check whether a capability is used by going to the OneExtend Usages table. | | OneExtend Builder Config | sys_one_extend_builder_config | Determines which capability and provider is related to each builder component for Workflow Studio and Virtual Agent Designer. | | OneExtend Builder Capability | sys_one_extend_builder_capability | Definitions for a capacity and its provider for builder components. | | OneExtend Usage | sys_one_extend_usage | Each usage of a capability in a Workflow Studio or Virtual Agent Designer topic, as well as any scripts such as business rules or UI actions. | | Gen AI Log Metadata | sys_gen_ai_log_metadata | Logs data about requests to the LLMs, including information about definition, errors, user, and feedback provided. AI-generated content can be tracked for a duration beyond six months with Now Assist configuration option. You can export historical data by writing a script to copy it into a different table without deleting the information. | | Generative AI Metric | sys_generative_ai_metric | Logs various metrics to evaluate LLM response performance and accuracy, including edit score, edit distance, guardrail activity, and LLM model details. It also records sensitive topic triggers and their scores for safety monitoring. | | Gen AI Model Version Mapping | sys_gen_ai_model_version_mapping | Maintains mappings between AI model versions, their providers, and configuration details, providing a clear understanding of how source models map to target models. It also includes associated metadata, such as skill type, model type, resource associations, and provider information. | | Generative AI Log | sys_generative_ai_log | Logs Generative AI prompts, responses, and edited responses for debugging LLM calls. HR-related logs are exclusively restricted to HR Administrators, ensuring sensitive information remains protected. For more information, see [Generative AI Controller tables](https://www.servicenow.com/docs/7bc5o3_fgkCkbo0AI4yIVQ "Generative AI Controller use dedicated tables to log AI activities and track Now Assist usage across Now Assist capabilities."). | [ ] ## Properties {#reference-for-generative-ai-controller__entry__35} | Property | Description | |-|-| | com.sn.generative.ai.provider | Default provider when capability definition has no default. Type: choice list No default value | | com.sn.generative.ai.ais.message | Message that is displayed when AI Search fails to find an answer to a query. Type: string Default value: No answer found. | | com.sn.generative.ai.log_prompt | Prompt that determines whether generative AI API calls are logged. Type: true \| false Default value: true | | com.sn.generative.ai.moderation.message | Message that is displayed if the OpenAI or Azure OpenAI moderation tools identify the content that goes against their terms of service. Type: string Default value: The response cannot be displayed as it's deemed inappropriate by OpenAI. | | com.glide.one.extend.token.buffer | Buffer that checks the request for the number of tokens before a OneExtend capability is executed. The maximum allowed request tokens are calculated based on the maximum tokens that are permitted by the AI provider's API minus the response token and buffer value that is specified in this system property. Type: integer Default value: 250 | | domain.llm.usage.entitled | Determines if a specific domain has permission to use the Now Assist features and whether to use the Large Language Model (LLM) to process data for that domain or restrict its use. Type: true \| false Default value: true Note: Setting `domain.llm.usage.entitled` to false, prevents a domain and its child domains from using Now Assist. | [Table 1. Generative AI Controller properties] ## External links {#reference-for-generative-ai-controller__entry__50} | Provider | Data policy | Usage policy | |-|-|-| | Amazon Bedrock | [Data protection](https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html) | [AWS Service Terms](https://aws.amazon.com/service-terms/) | | | | | | Google Cloud | [Google Cloud Platform Terms of Service](https://cloud.google.com/terms) | [Google Cloud Platform Terms of Service](https://cloud.google.com/terms) | | IBM watsonx | [Keeping your data secure and compliant](https://www.ibm.com/docs/en/watsonx/saas?topic=security-keeping-your-data-secure-compliant) | [Foundation model terms of use in watsonx.ai](https://www.ibm.com/docs/en/watsonx/saas?topic=solutions-terms-use) | | Microsoft Azure OpenAI | [Data, privacy, and security for Azure OpenAI Service](https://learn.microsoft.com/en-us/legal/cognitive-services/openai/data-privacy) | [Code of conduct for Azure OpenAI Service](https://learn.microsoft.com/en-us/legal/cognitive-services/openai/code-of-conduct) | | OpenAI | [API data usage policies](https://openai.com/policies/api-data-usage-policies) | [Usage policies](https://openai.com/policies/usage-policies) | [ ]